INDEX

Explanations

ask

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èµ·äºĨ

-0.31

ä¹ĭä¸Ĭ

-0.29

èĪĨ

-0.26

åĿıäºĭ

-0.26

rum

-0.26

earn

-0.26

à¸ļà¸²

-0.26

é¥½

-0.25

oro

-0.25

 Fate

-0.25

POSITIVE LOGITS

[âĢ¦]

0.27

({...

0.26

nable

0.25

/MIT

0.25

çĲĨäºĭéķ¿

0.24

sse

0.24

æ·±åĪ»

0.24

man

0.23

tox

0.23

(mx

0.23

Activations Density 0.143%

ask

No Comments

No Known Activations